Re: [PATCH v8 16/19] locking/rwsem: Guard against making count negative

[Peter Zijlstra]

On Mon, May 20, 2019 at 04:59:15PM -0400, Waiman Long wrote:
>  static struct rw_semaphore __sched *
> +rwsem_down_read_slowpath(struct rw_semaphore *sem, int state, long adjustment)
>  {
> +	long count;
>  	bool wake = false;
>  	struct rwsem_waiter waiter;
>  	DEFINE_WAKE_Q(wake_q);
>  
> +	if (unlikely(!adjustment)) {
> +		/*
> +		 * This shouldn't happen. If it does, there is probably
> +		 * something wrong in the system.
> +		 */
> +		WARN_ON_ONCE(1);

	if (WARN_ON_ONCE(!adjustment)) {

> +
> +		/*
> +		 * An adjustment of 0 means that there are too many readers
> +		 * holding or trying to acquire the lock. So disable
> +		 * optimistic spinning and go directly into the wait list.
> +		 */
> +		if (rwsem_test_oflags(sem, RWSEM_RD_NONSPINNABLE))
> +			rwsem_set_nonspinnable(sem);

ISTR rwsem_set_nonspinnable() already does that test, so no need to do
it again, right?

> +		goto queue;
> +	}
> +
>  	/*
>  	 * Save the current read-owner of rwsem, if available, and the
>  	 * reader nonspinnable bit.